Closed beasteers closed 3 years ago
@justinsalamon I don't have permissions to merge either of them so imma need u to merge the models first ;p
doh! on it
@beasteers model merged!
@justinsalamon this looks all good too! whenever you're ready I think we're good to merge.
Figured I would push this out while I'm waiting for something else to build.
Related PR containing updated models: https://github.com/marl/openl3/pull/61
Setup Changes
tensorflow>=2.0.0
and installs it by default (there is no longer a separate GPU package)kapre>=0.3.5
- TODO: make sure we have the exact minimum kapre version - I remember checking git blame, but haven't tested anythingRuntimeError: Cython >= 0.23.4 is required to build scikit-image from git checkout
)Doc Changes
Code Changes
get_audio_embedding(frontend='auto')
,process_audio_file(frontend='auto')
,process_video_file(audio_frontend='auto')
preprocess_audio(y, sr, input_repr=None)
that encapsulates the librosa frontend (as well as preprocessing for the kapre frontend)input_repr
and for kapre inputs, you leaveinput_repr=None
--audio-frontend
)load_audio_embedding_model(frontend='kapre')
get_stft_magnitude_layer
kapre_v0_1_4_magnitude_to_decibel
)Test Changes
pytest.mark.parameterize
to avoid doubling the length of the tests for testing frontendsDev Util Changes
tests/generate_regression.py
which generates new regression datatests/package_weights.py
which takes the weights files in the openl3 package folder and gzips them for git pushtests/migration/remove_layers.py
which lets us strip out the spectrogram (or any other) layerstests/migration/
has a few other analysis things/notebooks that were used early on in the frontend testingBefore merging: